linkedin-ads-35-point-audit
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data such as LinkedIn CSV exports, CRM data, and creative content.
- Ingestion points: Campaign Performance reports (CSV), Demographics reports (CSV), CRM data (Tier 3), and landing page URLs (Tier 4) as described in
SKILL.md. - Boundary markers: The skill does not define specific boundary markers or instructions to ignore embedded prompts in the data it parses.
- Capability inventory: The skill uses basic Python (
pandas) for data parsing and performs analytical reporting. It does not have network-write or persistent file-system modification capabilities. - Sanitization: No explicit sanitization of input data is defined in the instructions.
- [DATA_EXPOSURE]: The skill includes external links to marketing and attribution tools at
impactable.comanddemandsense.com. These references are consistent with the skill's stated purpose for ad auditing and attribution.
Audit Metadata